A pattern mining approach to enhance the accuracy of collaborative filtering in sparse data domains

Ramezani, Mohsen; Moradi, Parham; Akhlaghian, Fardin

doi:10.1016/j.physa.2014.04.002

Cited by 57 publications

(16 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The model considers the local context information of user ratings, as well as the global preference of user behavior. Ramezani et al [25] propose a method to find the neighbor users based on the users' interest patterns in order to overcome challenges like sparsity and computational issues, following the idea that users who are interested in the same set of items share similar interest patterns, therefore, the non-redundant item subspaces are extracted to indicate the different patterns of interest and then, a user's tree structure is created based on the patterns she has in common with the active user.…”

Section: Related Workmentioning

confidence: 99%

Using Time Clusters for Following Users’ Shifts in Rating Practices

Margaris

Vassilakis

2018

J. Complex Syst. Inform. Model. Q.

View full text Add to dashboard Cite

Abstract. Users that enter ratings for items follow different rating practices, in the sense that, when rating items, some users are more lenient, while others are stricter. This aspect is taken into account by the most widely used similarity metric in user-user collaborative filtering, namely, the Pearson Correlation, which adjusts each individual user rating by the mean value of the ratings entered by the specific user, when computing similarities. However, a user's rating practices change over time, i.e. a user could start as strict and subsequently become lenient or vice versa. In that sense, the practice of using a single mean value for adjusting users' ratings is inadequate, since it fails to follow such shifts in users' rating practices, leading to decreased rating prediction accuracy. In this work, we address this issue by using the concept of dynamic averages introduced earlier and we extend earlier work by (1) introducing the concept of rating time clusters and (2) presenting a novel algorithm for calculating dynamic user averages and exploiting them in useruser collaborative, filtering implementations. The proposed algorithm incorporates the aforementioned concept and is able to follow more successfully shifts in users' rating practices. It has been evaluated using numerous datasets, and has been found to introduce significant gains in rating prediction accuracy, while outperforming the dynamic average computation approaches that are presented earlier.

show abstract

Section: Related Workmentioning

confidence: 99%

Using Time Clusters for Following Users’ Shifts in Rating Practices

Margaris

Vassilakis

2018

J. Complex Syst. Inform. Model. Q.

View full text Add to dashboard Cite

show abstract

“…The obtained clusters contribute to provision of the recommendation, so that new items are suggested to the target user by evaluating the average ratings of the unrated items. Moreover, Ramezani et al [14] proposed a clustering algorithm by using a specific pattern mining approach to group the users.…”

Section: Clustering In Recommender Systemsmentioning

confidence: 99%

“…neighbor users) are used to produce suitable recommendations to a given user (i.e. an active user) in the recommendation process [1,[8][9][10][11][12][13][14][15][16]. The CF approach uses rates of the active user to previously purchased items to make recommendations.…”

Section: Introductionmentioning

confidence: 99%

“…Up to now, several model-based methods have been proposed in the literature. These methods include probabilistic models [19,21,22], clustering models [8,13,23,24], dimensionality reduction techniques [25,26], pattern mining approach [14], latent semantic models [20], and Markov decision process-based CF systems [22,27]. A review of research indicates that memory-based techniques are widely used as compared to model-based techniques [10,[28][29][30].…”

Section: Introductionmentioning

confidence: 99%

“…Although it has been shown that clustering-based CF approaches are useful methods to deal with the cold start problem, these methods also suffer from several shortcomings. Determining the correct number of clusters is the main issue in some of the clustering methods (such as k-means and fuzzy c-means) because the performance of the methods depends on predefining the optimal number of clusters [8,11,14,23,41,42]. Another problem is about usefulness of the identified clusters.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

An effective trust-based recommendation method using a novel graph clustering algorithm

Moradi

Ahmadian

Akhlaghian

2015

Physica A: Statistical Mechanics and its Applications

Self Cite

121

View full text Add to dashboard Cite

Recommendation algorithm based on community structure and user trust

Guo

Yang

et al. 2021

Concurrency and Computation

View full text Add to dashboard Cite

While contemporary community-based recommendation algorithms based on a single community structure are more capable of processing large datasets than ever, they lack recommendation precision. This article proposes a collaborative filtering recommendation algorithm that integrates community structure and user implicit trust. The algorithm first applies a method based on the Gaussian function to fill the matrix of item ratings of users to alleviate data sparsity. It then uses the trust matrix to obtain the asymmetric trust relationship of the trustor and trustee, based on which the degree of users' implicit trust is calculated. The users are divided into communities based on the implicit trust degree to determine the influence among users more accurately.The algorithm then predicts the target user's rating using the ratings of users in the community to generate recommendations. To verify the performance of the proposed algorithm, we compared the proposed algorithm with three contemporary algorithms under the same conditions using FilmTrust datasets. The recommendation accuracy as well as the mean absolute error and root mean square error values of the proposed algorithm were better than those of the other four algorithms by approximately 14% and 4%, respectively. The experimental results demonstrate that the proposed algorithm can achieve better recommendation efficiency than existing algorithms.

show abstract

A pattern mining approach to enhance the accuracy of collaborative filtering in sparse data domains

Cited by 57 publications

References 31 publications

Using Time Clusters for Following Users’ Shifts in Rating Practices

Using Time Clusters for Following Users’ Shifts in Rating Practices

An effective trust-based recommendation method using a novel graph clustering algorithm

Recommendation algorithm based on community structure and user trust

Contact Info

Product

Resources

About